mlsanityData to 14 Oct 2026

Speech to Speech Translation with Translatotron: A State of the Art Review

arXiv 2502.05980 ↗First posted 9 Feb 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

A cascade-based speech-to-speech translation has been considered a benchmark for a very long time, but it is plagued by many issues, like the time taken to translate a speech from one language to another and compound errors. These issues are because a cascade-based method uses a combination of methods such as speech recognition, speech-to-text translation, and finally, text-to-speech translation. Translatotron, a sequence-to-sequence direct speech-to-speech translation model was designed by Google to address the issues of compound errors associated with cascade model. Today there are 3 versions of the Translatotron model: Translatotron 1, Translatotron 2, and Translatotron3. The first version was designed as a proof of concept to show that a direct speech-to-speech translation was possible, it was found to be less effective than the cascade model but was producing promising results. Translatotron2 was an improved version of Translatotron 1 with results similar to the cascade model. Translatotron 3 the latest version of the model is better than the cascade model at some points. In this paper, a complete review of speech-to-speech translation will be presented, with a particular focus on all the versions of Translatotron models. We will also show that Translatotron is the best model to bridge the language gap between African Languages and other well-formalized languages.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

16 of 35 references.

References · 16

  1. 2017Word Translation Without Parallel Datacited by 487
  2. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  3. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
  4. 2021Direct speech-to-speech translation with discrete unitscited by 149
  5. 2017Sequence-to-Sequence Models Can Directly Translate Foreign Speechcited by 121
  6. 2019Direct speech-to-speech translation with a sequence-to-sequence modelcited by 118
  7. 2019Neural Machine Translation: A Review and Surveycited by 100
  8. 2021Translatotron 2: High-quality direct speech-to-speech translation with voice preservationcited by 71
  9. 2022UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Unitscited by 60
  10. 2021Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?cited by 54
  11. 2022TranSpeech: Speech-to-Speech Translation With Bilateral Perturbationcited by 34
  12. 2022Speech-to-Speech Translation For A Real-world Unwritten Languagecited by 25
4 more
  1. 2023Translatotron 3: Speech to Speech Translation with Monolingual Datacited by 12
  2. 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialectscited by 11
  3. 2023`Ir`oy`inSpeech: A multi-purpose Yor`ub'a Speech Corpuscited by 7
  4. 2024Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?cited by 4

Built on by

Not cited yet.